Negligible Error Research Articles

Machine learning-based predictive model for temperature and comfort parameters in indoor enviroment using experimantal data

The research introduces an artificial neural network model that predicts temperature and assesses thermal comfort metrics for a cooling room, demonstrating how machine learning advancements can enhance thermal efficiency and cost-effectiveness in building design. The study utilized the Levenberg-Marquardt (LM) artificial neural network (ANN) approach to derive the average temperature and thermal comfort metrics collected under actual operating settings. The Predicted Mean Vote (PMV) and Predicted Percentage Dissatisfied (PPD)values were measured at three distinct sites and then compared to the trial findings. The model uses a dataset of 205 observations, with 143 cases used for training and 31 examples for testing and validation. The ANN model demonstrated effective training, with negligible errors in estimated error values. The mean squared error values for average temperature and thermal comfort parameters were 0.0342, 0.0376, 0.0571, 0.0029, and 0.2296. The R values for temperature measurements are 0.9947 and 0.9923, 0.9847 and 0.9437, and 0.9737, demonstrating a highly effective engineering method. The ANN model provided precise predictions for temperature and thermal comfort metrics, such as PMV and PPD in a cooling chamber, with a tolerance of ± 15 %. The LM approach, a machine learning methodology, produced excellent outcomes, particularly at lower temperatures, with 15 % of the data exceeding this range.

An Online Data-Driven Method for Accurate Detection of Thermal Updrafts Using SINDy

Utilizing thermal updrafts shows potential for enabling long-endurance cruising of fixed-wing unmanned aerial vehicles without energy consumption. This article presents a novel online method based on sparse identification of nonlinear dynamics (SINDy) approach to achievement identification of thermal sources in the atmosphere. Initially, the algorithm is incorporated into the upper-level planning system, interacting with the lower-level controller. Then, experiments are conducted through software-in-the-loop simulations (SITL) to validate the implementation of the proposed algorithm. It is found that direct observation of thermal sources through measurements using SINDy is unfeasible during straight and circular flight modes. Nevertheless, simulation analysis of the proposed approach indicates that under unobservable conditions, a portion of the parameters can still be identified. By comparing results obtained using the particle filter algorithm, this method is shown to accurately estimate the parameters with negligible errors under observability conditions. The novelty of this approach lies in its significant improvement of the localization accuracy of the thermal source, without the need for parameter adjustments in the algorithm. Finally, the proposed methods are integrated into commonly used hardware platforms, and their online feasibility is verified through hardware-in-the-loop simulations.

Neuro-modelling and fuzzy logic control of a two-wheeled wheelchair system

Two-wheeled wheelchairs have been used as alternatives for the elderly and disabled people to perform physical activities due to their restriction of movement. Significant challenges posed by two-wheeled wheelchairs control due to their inherent instability, resembling that inverted pendulum system. This research addresses these challenges by developing a dynamic non-linear model and stability control using computational algorithms. A neural network-based Nonlinear Autoregressive model with Exogenous Inputs (NARX) was developed, capturing and behaving similar to the complex dynamics of the wheelchair system with the identification on the experimental input–output data. Ensuring stable and responsive control, design of optimized PD-type and PID-type fuzzy logic controllers using Particle Swarm Optimization (PSO) were established and were tested under a simulation environment. The performance was evaluated across various metrics, including Integral Squared Error (ISE), Integral Absolute Error (IAE), Mean Squared (MSE), and Integral Time Absolute Error (ITAE). The result demonstrates that the PSO Optimized PID-type fuzzy logic controller with scaling factor from MSE index performance come out as best overall, significantly outperforms PD-type fuzzy logic controller, reducing its settling time by 12.5% to 35 s, minimizing overshoot to 0.81°, and achieving a negligible steady-state error of 0.046%. These results highlight the significant of integrating fuzzy logic control and PSO to the neural network model in enhancing the stability and performance of two-wheeled wheelchair systems, offering user safety and comfort.

A Bayesian regularization radial basis neural network novel procedure for the fractional economic and environmental system

The motive of current work is to design a novel radial basis Bayesian regularization neural network (RB-BRNN) for solving the nonlinear fractional economic and environmental system (FEES). A radial basis activation function in the hidden layers is applied by taking 20 numbers of neurons. The mathematical FEES is presented in three classes, named as cost of control accomplishment, manufacturing elements competence and technical exclusion’s diagnostics cost. A reference dataset is obtained using the Adams numerical results to reduce the mean square error (MSE) by taking the data for training 70%, while 15% is used for both testing and validation. The negligible absolute error values and comparison of the solutions develop the worth of computing RB-BRNN in order to solve the nonlinear dynamics of the FEES. Error diagrams, regression values, and the MSE performances are implemented to assess the precision of the designed solver.

Using Supervised and Unsupervised Machine Learning Models to Analyze Students Academic Performance

Examination result repositories generated by most universities can serve as machine learning datasets for training various models to gain insights from the data. These datasets can train multiple linear regression models to determine a student's cumulative grade point average (CGPA), or the score that a student will get in specific courses. Additionally, classification-based supervised machine learning models can use these datasets to provide insights into the class result that a student will obtain. These insights can be invaluable for academic advising and early intervention. Moreover, these datasets can train clustering-based unsupervised machine learning models, such as the K-means clustering model, to understand how student results are grouped into various clusters. This information can be crucial for planning and evaluating the quality of the university. This paper uses the dataset of undergraduate students' examination results from the Department of Computer Science at the University of Nigeria, Nsukka, to train three supervised machine learning models and one unsupervised machine learning model, utilizing Jupyter Notebook as the Python IDE. The training results showed acceptable accuracies of 91.5% for the Naïve Bayes model and 95.1% for the Decision Tree model. The linear regression model demonstrated a negligible root mean square error of 8.23×10−18, while the K-means clustering model exhibited an acceptable Silhouette metric of 0.12.

Enhancing stability and position control of a constrained magnetic levitation system through optimal fractional-order PID controller

Magnetic levitation systems are complex and nonlinear, requiring sophisticated control methods to maintain the stability and position of the levitated object. This research presents an optimized fractional order PID (FOPID) control approach for position control of a freely-suspended ferromagnetic object. The dynamic system model is mathematically modeled in MATLAB using first-principle modeling and the grey box method. The FOPID controller has five degrees of freedom (DOFs) that allow for fine-tuning of the control gains and fractional orders, enabling the system to handle the nonlinearity inherent in the magnetic levitation system. The DOFs of FOPID and integer order PID controllers are optimized using the Artificial Bee Colony (ABC) algorithm and results are compared with state-of-the-art optimization methods. The results showed that the FOPID controller can effectively control the magnetic levitation system with constraints and outperforms other methods by up to 92.14% in terms of settling time with negligible steady-state error.

Development of an external system for monitoring the couch speed in radiotherapy using continuous bed movement.

Total body irradiation before bone marrow transplantation for hematological malignancies using Radixact, a high-precision radiotherapy machine, can potentially reduce side effects and the risk of secondary malignancies. However, stable control of couch speed is critical, and direct assessment methods outlined in quality assurance guidelines are lacking. This study aims to develop a real-time couch speed verification system for the Radixact. The developed system used a linear encoder to measure couch speed directly. Accuracy was verified via a linear stage, comparing measurements with a laser distance sensor. After placing a phantom simulating the human body on the Radixact couch, the couch speed was verified using predefined speed plans. Operating the linear stage at 0.1, 0.5, and 1.0mm/s revealed that the maximum position error of the developed verification system compared to the laser distance sensor was nearly equivalent to the distance resolution of the system (0.05mm/pulse), with negligible average speed error. When the Radixact couch operated at 0.1, 0.5, and 1.0mm/s, the values obtained by the verification system agreed with the theoretical values within the sampling period (0.01s) and distance resolution (0.05mm). The verification system developed provides real-time monitoring of the speed of the Radixact table, ensuring treatment effectiveness and patient safety. It would guarantee the couch speed's soundness and contribute to the "visualization" of safety.

Red-Billed Blue Magpie Optimizer for Electrical Characterization of Fuel Cells with Prioritizing Estimated Parameters

The red-billed blue magpie optimizer (RBMO) is employed in this research study to address parameter extraction in polymer exchange membrane fuel cells (PEMFCs), along with three recently implemented optimizers. The sum of squared deviations (SSD) between the simulated and measured stack voltages defines the fitness function of the optimization problem under investigation subject to a set of working constraints. Three distinct PEMFCs stacks models—the Ballard Mark, Temasek 1 kW, and Horizon H-12 units—are used to illustrate the applied RBMO’s feasibility in solving this challenge in comparison to other recent algorithms. The highest percentages of biased voltage per reading for the Ballard Mark V, Temasek 1 kW, and Horizon H-12 are, respectively, +0.65%, +0.20%, and −0.14%, which are negligible errors. The primary characteristics of PEMFC stacks under changing reactant pressures and cell temperatures are used to evaluate the precision of the cropped optimized parameters. In the final phase of this endeavor, the sensitivity of the cropped parameters to the PEMFCs model’s performance is investigated using two machine learning techniques, namely, artificial neural network and Gaussian process regression models. The simulation results demonstrate that the RBMO approach extracts the PEMFCs’ appropriate parameters with high precision.

The BiCG Algorithm for Solving the Minimal Frobenius Norm Solution of Generalized Sylvester Tensor Equation over the Quaternions

In this paper, we develop an effective iterative algorithm to solve a generalized Sylvester tensor equation over quaternions which includes several well-studied matrix/tensor equations as special cases. We discuss the convergence of this algorithm within a finite number of iterations, assuming negligible round-off errors for any initial tensor. Moreover, we demonstrate the unique minimal Frobenius norm solution achievable by selecting specific types of initial tensors. Additionally, numerical examples are presented to illustrate the practicality and validity of our proposed algorithm. These examples include demonstrating the algorithm’s effectiveness in addressing three-dimensional microscopic heat transport and color video restoration problems.

Establishing the longitudinal hemodynamic mapping framework for wearable-driven coronary digital twins

Understanding the evolving nature of coronary hemodynamics is crucial for early disease detection and monitoring progression. We require digital twins that mimic a patient’s circulatory system by integrating continuous physiological data and computing hemodynamic patterns over months. Current models match clinical flow measurements but are limited to single heartbeats. To this end, we introduced the longitudinal hemodynamic mapping framework (LHMF), designed to tackle critical challenges: (1) computational intractability of explicit methods; (2) boundary conditions reflecting varying activity states; and (3) accessible computing resources for clinical translation. We show negligible error (0.0002–0.004%) between LHMF and explicit data of 750 heartbeats. We deployed LHMF across traditional and cloud-based platforms, demonstrating high-throughput simulations on heterogeneous systems. Additionally, we established LHMFC, where hemodynamically similar heartbeats are clustered to avoid redundant simulations, accurately reconstructing longitudinal hemodynamic maps (LHMs). This study captured 3D hemodynamics over 4.5 million heartbeats, paving the way for cardiovascular digital twins.

Extracting dashcam telemetry data for predicting energy use of electric vehicles

Prior to the acquisition of an electric vehicle, pre-evaluation of vehicle energy use is desirable to assess whether the intrinsic vehicle electrical storage capability is satisfactory. However, inconsistency in general vehicle modelling may provide unreliable predictions concerning energy usage. To increase the prediction reliability, the use of route-specific driving cycle data is essential.This paper presents a case study of a novel method of extracting vehicle telemetry data from archived dashcam videos without the need to deploy conventional telemetry techniques. Utilising dashcam videos as input, and employing image processing and recognition technology, textual en-route driving data embedded in the video can be extracted. This data can then, in-turn, be used to model the performance of the vehicle, or an electric equivalent in terms of energy use and emissions. Results from preliminary testing with real-life dashcam videos, demonstrate negligible errors with regards to energy requirements and pollutants emitted from an EV operating on the modelled routes. Consequently, the proposed solution opens up the possibility to gather a significant amount of new data in order to better assess the transport sector’s energy requirements. This is especially important for situations where conventional telemetry is difficult to obtain. In addition, results from vehicle fleet modelling may inform policy decisions with regard to the impact of introducing low emission zones.

Tensor hypercontraction for fully self-consistent imaginary-time GF2 and GWSOX methods: Theory, implementation, and role of the Green's function second-order exchange for intermolecular interactions.

We present an efficient MPI-parallel algorithm and its implementation for evaluating the self-consistent correlated second-order exchange term (SOX), which is employed as a correction to the fully self-consistent GW scheme called scGWSOX (GW plus the SOX term iterated to achieve full Green's function self-consistency). Due to the application of the tensor hypercontraction (THC) in our computational procedure, the scaling of the evaluation of scGWSOX is reduced from O(nτnAO5) to O(nτN2nAO2). This fully MPI-parallel and THC-adapted approach enabled us to conduct the largest fully self-consistent scGWSOX calculations with over 1100 atomic orbitals with only negligible errors attributed to THC fitting. Utilizing our THC implementation for scGW, scGF2, and scGWSOX, we evaluated energies of intermolecular interactions. This approach allowed us to circumvent issues related to reference dependence and ambiguity in energy evaluation, which are common challenges in non-self-consistent calculations. We demonstrate that scGW exhibits a slight overbinding tendency for large systems, contrary to the underbinding observed with non-self-consistent RPA. Conversely, scGWSOX exhibits a slight underbinding tendency for such systems. This behavior is both physical and systematic and is caused by exclusion-principle violating diagrams or corresponding corrections. Our analysis elucidates the role played by these different diagrams, which is crucial for the construction of rigorous, accurate, and systematic methods. Finally, we explicitly show that all perturbative fully self-consistent Green's function methods are size-extensive and size-consistent.

Enhancing Fishing Efficiency with Geographic Information System and Optimized Methods

Traditional fishing techniques frequently lack efficiency and optimization, resulting in fishermen obtaining unsatisfactory yields. This study presents a novel approach by incorporating Geographic Information System (GIS) technology, notably utilizing Leaflet, to improve fishing techniques. The suggested system incorporates a LoRa node tool that logs the journeys of fishermen, offering comprehensive itineraries and data on the distribution of fish and unfavorable weather conditions. Notable outcomes were attained by employing the haversine approach to compute distances between the LoRa Gateway and different data points. The approach exhibited a negligible error margin of 0.157% in contrast to the calculations performed in Excel. In addition, the GPS accuracy testing produced remarkable results, with latitude and longitude errors of 0.000116% and 0.000002%, respectively. The LoRa system demonstrated a range of RSSI performance, with values ranging from -57 dBM at 50 meters to -121 dBM at 1500 meters. This range of performance guarantees dependable transmission of data over significant distances. The findings underscore the GIS-based strategy's efficacy in enhancing the effectiveness and precision of conventional fishing methods, presenting a promising technical improvement for the fishing sector.

Stabilized oily-wastewater separation based on superhydrophilic and underwater superoleophobic ceramic membranes: Integrated experimental design and standalone machine learning algorithms

BackgroundReliable computational approaches to evaluate ceramic membrane performance in wastewater treatment mark a transformative step towards optimizing separation processes, ensuring environmental sustainability, and advancing water purification technologies. The current study explores the influential factors using artificial intelligence (AI) tools in the performance evaluation of superhydrophilic and underwater super-oleophobic ceramic membranes for the selective treatment of oily wastewater. MethodsThe chemometrics scenario of the research based on established experimental work employs advanced AI models viz: Random Forest (RF), Support Vector Regression (SVR), and Gaussian Process Regression (GPR) to predict the efficacy of these membranes in terms of rejection and flux. The model predictions were evaluated using the Pearson Correlation Coefficient (PCC), Willmott Index (WI), mean absolute percentage error (MAPE), and mean absolute error (MAE). Significant findingsFrom the results, GPR had shown good agreement with correlations (WI=99.9) during the training and testing phases for flux prediction, indicating an exceptional model fit with negligible error (MAPE=0.001, MAE=0.000 in the testing phase). For rejection modelling, GPR and SVR exhibit similar levels of accuracy, with moderate PCC and WI values, while RF reveals significant limitations with the lowest scores across all statistical metrics. The findings highlight the potential of AI in optimizing wastewater treatment processes, with GPR identified as the most promising model for flux prediction. This study would provide insight into the modelling of the membrane separation process for oily wastewater and integrate AI in the performance evaluation of wastewater reclamation.

Wages: The Worst Transistor Aging Analysis for Large-scale Analog Integrated Circuits via Domain Generalization

Transistor aging leads to the deterioration of analog circuit performance over time. The worst aging degradation is used to evaluate the circuit reliability. It is extremely expensive to obtain it since several circuit stimuli need to be simulated. The worst degradation collection cost reduction brings an inaccurate training dataset when a machine learning (ML) model is used to fast perform the estimation. Motivated by the fact that there are many similar subcircuits in large-scale analog circuits, in this article we propose Wages to train an ML model on an inaccurate dataset for the worst aging degradation estimation via a domain generalization technique. A sampling-based method on the feature space of the transistor and its neighborhood subcircuit is developed to replace inaccurate labels. A consistent estimation for the worst degradation is enforced to update model parameters. Label updating and model updating are performed alternately to train an ML model on the inaccurate dataset. Experimental results on the very advanced 5 nm technology node show that our Wages can significantly reduce the label collection cost with a negligible estimation error for the worst aging degradations compared to the traditional methods.

Eye-Net: A Low-Complexity Distributed Denial of Service Attack-Detection System Based on Multilayer Perceptron

Distributed Denial of Service (DDoS) attacks disrupt service availability, leading to significant financial setbacks for individuals and businesses. This paper introduces Eye-Net, a deep learning-based system optimized for DDoS attack detection that combines feature selection, balancing methods, Multilayer Perceptron (MLP), and quantization-aware training (QAT) techniques. An Analysis of Variance (ANOVA) algorithm is initially applied to the dataset to identify the most distinctive features. Subsequently, the Synthetic Minority Oversampling Technique (SMOTE) balances the dataset by augmenting samples for under-represented classes. Two distinct MLP models are developed: one for the binary classification of flow packets as regular or DDoS traffic and another for identifying six specific DDoS attack types. We store MLP model weights at 8-bit precision by incorporating the quantization-aware training technique. This adjustment slashes memory use by a factor of four and reduces computational cost similarly, making Eye-Net suitable for Internet of Things (IoT) devices. Both models are rigorously trained and assessed using the CICDDoS2019 dataset. Test results reveal that Eye-Net excels, surpassing contemporary DDoS detection techniques in accuracy, recall, precision, and F1 Score. The multiclass model achieves an impressive accuracy of 96.47% with an error rate of 8.78%, while the binary model showcases an outstanding 99.99% accuracy, maintaining a negligible error rate of 0.02%.

Absolute testing of rotationally symmetric surfaces with computer-generated holograms

Extremely high accuracy is demanded for optics working at very short wavelength. Interferometric testing of optical aspheres or freeform surfaces requires null optics, typically computer-generated holograms (CGHs), to balance the wave aberrations. The measurement uncertainty is primarily limited by the accuracy of the test wavefront, which is predominantly influenced by the CGH and the interferometer optics. Absolute testing is fundamental to achieving accuracy much higher than that of the test wavefront through error separation. This paper presents a method for absolute testing of rotationally symmetric surfaces with CGH null optics. The basic assumption is that the off-axis hologram fabricated by raster scanning beam writing has negligible error of rotationally symmetric component due to pattern error of the CGH. Consequently, the wavefront error contributed by the CGH and the transmission flat can be completely separated from the absolute surface shape by combining the N-position method and the shift-rotation method. A theoretical model for absolute testing is proposed under the assumption. Experimental cross test is then presented to validate the method with sub-nanometer uncertainty. The assumption is further confirmed by characterizing the fabrication error of the hologram structures using a white light interferometer. Finally, the effect of noise, translation error, rotation error and eccentricity of rotation on the absolute testing is analyzed.

Proposing a novel nonlinear integrated control technique for an electric power steering system to improve automotive dynamic stability

This article proposes a new control solution for an electric power steering (EPS) system to ensure the stability of car's dynamic behaviours. This work provides two new contributions which differ from previously existing publications. Firstly, a novel control method for the steering system is designed in this article based on a combination of proportional-integral-derivative (PID) and backstepping control techniques. The input to the backstepping algorithm is the output of the PID controller, whose parameters are tuned by a complex fuzzy algorithm with two inputs. Secondly, values of road reaction torque and other dynamic effects are calculated using a complex automotive dynamics model based on a nonlinear motion model and a spatial oscillation model. The stability of the control system is evaluated through the Lyapunov control function and the error between the output signals, while the dynamic stability is evaluated through the changes in car's dynamic behaviours. According to the simulation results, output values always closely follow ideal values with negligible errors if and only when the steering system is controlled by the proposed algorithm. In some conditions, the steering motor angle error achieved by the proposed controller does not exceed 0.022 rad, much lower than the fault scenario. In addition, the vehicle's roll angle and motion trajectory always follow the desired value with minimal errors. In conclusion, if the EPS system is controlled by the new control technique shown in this article, car dynamic stability will be guaranteed under all investigated conditions.

Kinematics of nonlinear waves over variable bathymetry. Part I: Numerical modelling, verification and validation

Fluid particle kinematics due to wave motion (i.e. orbital velocities and accelerations) at and beneath the free surface is involved in many coastal and ocean engineering applications, e.g. estimation of wave-induced forces on structures, sediment transport, etc. This work presents the formulations of these kinematics fields within a fully nonlinear potential flow (FNPF) approach. In this model, the velocity potential is approximated with a high-order polynomial expansion over the water column using an orthogonal basis of Chebyshev polynomials of the first kind. Using the same basis, original analytical expressions of the components of velocity and acceleration are derived in this work. The estimation of particle accelerations in the course of the simulation involves the time derivatives of the decomposition coefficients, which are computed with a high-order backward finite-difference scheme in time. The capability of the numerical model in computing the particle kinematics is first validated for regular nonlinear waves propagating over a flat bottom. The model is shown to be able to predict both the velocity and acceleration of highly nonlinear and nearly breaking waves with negligible error compared to the corresponding stream function wave solution. Then, for regular waves propagating over an uneven bottom (bar-type bottom profile), the simulated results are confronted with existing experimental data, and very good agreement is achieved up to the sixth-order harmonics for free surface elevation, velocity and acceleration.

Enhancing curvature prediction in flexible printed circuits: A computational approach integrating analytical models with finite element simulations

This investigation presents an analytical model optimized for predicting the curve of Flexible Printed Circuits (FPCs), aiming to enhance design precision within the burgeoning realm of flexible electronics. By modifying the bending Mises stresses derived from the finite element model (FEM), an almost linear relationship was established between the deformed FPC curvature and its length. The analytical model, based on the trend of the FPC curve, integrates differential equations, the Jacobian matrix, and an iterative process. The model's performance, marked by its remarkable efficiency, is rigorously compared with Finite Element Method simulations. The results show a negligible error between the two methods, with the predicted results for different types of FPC curves proving to be highly accurate. The study's insights advocate for the model's adoption in practical applications, suggesting a paradigm shift towards more agile and efficient design methodologies in flexible electronics engineering.